© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1288
    Prev
    Next
    INDEX
    Explanations

    instances of interference and its effects on rights or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Interference or disruption

    np_acts-logits-general · gemini-2.0-flash

    interfere with disrupting undermine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.69
    OGND
    -0.56
     määrä
    -0.50
     bertanggung
    -0.47
     dévelo
    -0.46
     izvē
    -0.46
    scriptcase
    -0.45
    ArgsConstructor
    -0.44
     ympä
    -0.42
     comportements
    -0.42
    POSITIVE LOGITS
     disrupting
    0.60
     disrupt
    0.59
     disruption
    0.58
     mengganggu
    0.58
     interruption
    0.54
    ruptedException
    0.52
     interference
    0.52
     interrupting
    0.52
     disrupted
    0.50
     impair
    0.49
    Activations Density 0.683%

    No Known Activations